AWS adds usage-based metering to SageMaker AI bidi streaming
Start here
AWS announced usage-based metering for Amazon SageMaker AI bidirectional streaming inference, letting model providers report actual consumption to AWS Marketplace software charges during live sessions. Deepgram is the launch partner, bringing usage-based Speech-to-Text and Text-to-Speech billing to AWS Marketplace. The design adds a companion WebSocket metadata stream through which providers send incremental metering records, capped at one message per second per connection and 512 bytes per message. If that stream fails to establish or drops mid-session, inference continues by default, since the metadata-stream-required header defaults to false. Metering does not replace infrastructure billing: SageMaker AI endpoint infrastructure charges still apply, and AWS advises deleting test endpoints after testing to avoid ongoing charges.
Generated from reports · updated 23 h ago
Report timeline
Follow the reports to see the event from different sides.
- AWS Machine Learning BlogAmazon SageMaker AI bidirectional streaming gains usage-based pricing, Deepgram as launch partner
Amazon SageMaker AI bidirectional streaming now supports usage-based metering, letting model providers report actual consumption to AWS Marketplace software charges while endpoint infrastructure fees still apply. Deepgram is the launch partner, bringing usage-based Speech-to-Text and Text-to-Speech billing to AWS Marketplace. The design adds a companion WebSocket metadata stream, capped at one message per second and 512 bytes, so providers can send incremental metering records during live sessions.
Heat for this event
Not enough continuous observations yet to draw a trend.